Dragonish

In my obsidian i use the daily note feature heavily and if i come across a useful snippet or info i will add a tag and content like below. I found tagging to be helpful because i do not have to spend effort up front putting the file in the “right” folder. I have cleaned some of these up by removing them from my daily notes and into dedicated notes, but only after i have collected quite a few for a specific language or tech and there is a need for me to put more structure around the information.

#codesnippet/<language or tech stack> Write a description to help me remember what this is for

<insert code here>

Super excited to see the expansion functionality released!

That has been my experience as well. Signing with SSH keys has been way easier to maintain over time than GPG. Plus you can use the same key to sign that you use for authentication to simplify system setup.

You are probably right, always check local laws when modifying your vehicle. Even if there are no laws you will probably run afoul of your insurer in some way.

One dreams of a day where it could be a thing. My take is that a drop in replacement is not possible because there is no incentive for car manufacturers to provide that hardware interoperability. They profit too much from the work google does to write the software for them, and all your data they can sell. They want you to buy a whole new car to get the latest features, they are not going to make it any easier on you to extend the lifetime of their product.

There are projects like Crankshaft that allow you to add a head unit to a vehicle that does not have one, but that does not get rid of the android app on your phone. As far as i know all these projects relay on a reverse engineered implementation of the android auto spec: https://github.com/f1xpl/openauto

One could read that implementation and make a client, but i am not aware of one that exists, let alone is actively maintained. Ibl believe the reason is the cost of testing the software for compatibility with all the different auto maker hardware makes this too difficult to sustain. I look forward to other responses to see what others are using.

Hosting my own git server on my NAS made my life easier and better due to the new freedoms it offers. Backups are centralized, and I have all the space i need to keep any interesting code safe. I am using forgjeo now and highly recommend it. You can also use other front ends (or none and just ssh/filesystem) but forgjeo gives me artifacts (ie docker registry), code search, LFS, and more. With my own git server, my local filesystem only has what I am working on recently (or as my workstation space allows). My home folder has a folder for each version control system (git, pijul, svn). Inside of these i have 2 sub folders: <domain>/<repo name>

Some examples of different domains are: open, work, personal, dragonish. I do not separate what forge or remote service in the filesystem, this is a persona boundary.

I use git remote names and branches in each repo to handle what software forge and any upstream/maintainers i need to work with. As an example my work repos only get pushed to my work server (ie, only 1 git remote named origin set to my work’s server), but my open ones will go to forgjeo and github (i setup 2 git remotes, origin and github. origin in this domain goes to my forgjeo). If i have a need i go into some more git branching strategy which I do find has helped me over my life, but I think I am overthinking this post now! keep it all simple enough for what your needs are.

I am loving the new release cadence!

my understanding is that terms of service would be helpful but not needed if someone trued to sue because you blocked access to the site. I would not expect ToS for a site like you are explaining, but if it did it would say “the web admin will ban you if you are naughty, you have been warned”

For privacy policy i think what you wrote to give us context is near perfect. Explain how your app stores data, be specific about encryption at rest and in motion. If your app is designed to hold name, email address, billing info you should highlight that in your policy. including a (monitored) contact email for questions would be nice, but not needed imo unless you are storing PII

Clouds and Feuds from Age Of Wonders

To expand with my personal experience, I self host a synapse server partly for the reason that i want my children (aged 8-14 now) to have a communication platform they can access to get ahold of me with out requireing a sim card. I do not federate, and i do not allow account sign ups. That keeps a pretty isolated instance while still allowing everyone on that homeserver to be able to talk to each other.

I help them get Element setup on each device. I dont think this is overly complicated, but i am sure i am a horrible judge of complexity… They have to enter the url of the server, then their password, then they need to scan a qr code/verify from an existing device. Or, they need to enter a second passcode to verify their identity. I help them keep those secrets in bitwarden, so imo, that complexity is an opportunity to explain some opsec and encryption!

For keeping track of tasks on my projects i use todo txt. For each of my projects will drop a file named todo.txt in the root. each line is a task, and i order them based on priority. I can walk away from it and when i start working on the project again, i have an simple way to see the list of tasks i have laid out for this project.

http://todotxt.org/

I personally find it less useful to see the “big picture” of all tasks, and this lets me focus on the details of my projects without forcing a bunch of structure.

I am using Mistral 7b Instruct for text summary and some light “assistant” type chatting for the last several months. I have been pleased at how accurate it is for my needs, especially given it’s size.

I recall alot of trial and error to find models that were compatible with the version of llama-cpp-python that oobabooga uses (at any given time). GGUF should have made the model format (and therefore model selection) more simple, but i imagine there are still nuances that make it more difficult than it should be to find a working model for a noob.

Best of luck, let us know how it goes